[all-commits] [llvm/llvm-project] 50a76a: [MLIR][NVGPU] Handling Offset in `nvgpu.tma.async....

[Guray Ozen via All-commits]

  Branch: refs/heads/main
  Home:   https://github.com/llvm/llvm-project
  Commit: 50a76a7d73dbe587aa07f6f9e1ec336612c16c5f
      https://github.com/llvm/llvm-project/commit/50a76a7d73dbe587aa07f6f9e1ec336612c16c5f
  Author: Guray Ozen <guray.ozen at gmail.com>
  Date:   2023-08-08 (Tue, 08 Aug 2023)

  Changed paths:
    M mlir/lib/Conversion/NVGPUToNVVM/NVGPUToNVVM.cpp
    M mlir/test/Conversion/NVGPUToNVVM/nvgpu-to-nvvm.mlir

  Log Message:
  -----------
  [MLIR][NVGPU] Handling Offset in `nvgpu.tma.async.load`

When using `nvgpu.tma.async.load` Op to asynchronously load data into shared memory, it fails to account for provided offsets, potentially leading to incorrect memory access. Using offset is common practice especially with the dynamic shared memory. This work addresses the problem by ensuring proper consideration of offsets.

Reviewed By: nicolasvasilache

Differential Revision: https://reviews.llvm.org/D157380